Summary: In a previous paper focused on four major rain-fed breadbasket crops—maize, rice, soybean and wheat—the author developed a set of crop yield statistical emulators and showed that they could produce results comparable to those generated by an ensemble of global gridded crop model (GGCM) simulations upon which they were trained. This new study provides statistical emulators of GGCMs to estimate irrigated crop yields and associated irrigation water withdrawals for maize, rice, soybean and wheat. Those emulators are estimated using data from an ensemble of simulations from five GGCMs from the Inter-Sectoral Impact Model Intercomparison Project Fast Track project. Crop-specific response functions for each GGCM are estimated at the grid-cell level over the globe. Validation exercises confirm that the statistical emulators are able to replicate the crop models’ spatial patterns of irrigated crop yields and irrigation water withdrawals reasonably well, both in terms of levels and changes over time, although accuracy varies by model and by region. This study therefore provides a reliable and computationally efficient alternative to global gridded crop models.